Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Although annotations already declare readOnlyHint=true, the description goes further: it emphasizes 'nothing is created or changed', warns about per-project currency and the risk of assuming it matches the user's business currency, discloses that results include a headline estimate/invoiced/still-to-invoice figure, and explains the meaning of a 401-style error (plan may lack Xero Projects or the connection needs reconnecting). This adds rich behavioral context beyond the annotations and is directly actionable for an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively long but every sentence earns its place: definition, read-only assurance, filter options, currency caveat, result content, alternative tool, and error interpretation. It is front-loaded with the core purpose and safety, then progressively adds operational detail, with no filler or repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description compensates by describing what each result contains (headline estimate/invoiced/still-to-invoice figure, currency-named values) and where to go for deeper detail. It also covers error handling, filtering, and multi-organisation setup. For a list tool with five optional parameters and no return schema, the description provides everything an agent needs to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful provenance: contactId is 'a Xero ContactID from list_xero_contacts', and organisation is only needed when the connection reaches more than one organisation, which clarifies parameter semantics beyond the raw schema. It does not repeat every parameter, but the added guidance is valuable and non-redundant.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'List job/project-costing projects from Xero Projects for the current organisation', and clarifies what these projects represent with concrete examples. It explicitly distinguishes the tool from the sibling get_xero_project by pointing to it for the full breakdown, making the purpose unambiguous against a large family of list_xero_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: when you need a filtered list of projects with headline figures, use this tool; when you need the full cost-and-earned breakdown on one project, use get_xero_project instead. It also tells the agent where to source contactId (from list_xero_contacts) and how to handle multi-organisation connections, leaving no ambiguity about when and how to invoke it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.